Classification of impervious land-use features using object-based image analysis and data fusion

The proportion of impervious area within a watershed is a key indicator of the impacts of urbanization on water quality and stream health. Research has shown that object-based image analysis (OBIA) techniques are more effective for urban land-cover classification than pixel-based classifiers and are...

Full description

Saved in:
Bibliographic Details
Published in:Computers, environment and urban systems environment and urban systems, 2019-05, Vol.75, p.103-116
Main Authors: Lichtblau, Ela, Oswald, Claire J.
Format: Article
Language:English
Subjects:
Automation
Classification
Data integration
Feature extraction
Image analysis
Image classification
Image resolution
Impervious areas
Land cover
Land use
Multisensor fusion
Remote sensing
Urban
Urbanization
Water quality
Workflow
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The proportion of impervious area within a watershed is a key indicator of the impacts of urbanization on water quality and stream health. Research has shown that object-based image analysis (OBIA) techniques are more effective for urban land-cover classification than pixel-based classifiers and are better suited to the increased complexity of high-resolution imagery. Focusing on five 2-km2 study areas within the Black Creek sub-watershed of the Humber River, this research uses eCognition® software to develop a rule-based OBIA workflow for semi-automatic classification of impervious land-use features (e.g., roads, buildings, Parking Lots, driveways). The overall classification accuracy ranges from 88.7 to 94.3%, indicating the effectiveness of using an OBIA approach and developing a sequential system for data fusion and automated impervious feature extraction. Similar accuracy results between the calibrating and validating sites demonstrates the strong potential for the transferability of the rule-set from pilot study sites to a larger area. •Object-based image analysis was used for semi-automatic classification on land-use features.•Overall impervious land-use feature classification accuracy ranges from 89 to 94%.•High accuracy for study areas used to validate the classification suggest the rule-set is transferable to larger areas.•Detailed impervious land-use feature maps could be used for estimating urban pollutant inputs and as a basis for calculating stormwater taxes.
ISSN:0198-9715
1873-7587
DOI:10.1016/j.compenvurbsys.2019.01.007